pptx
Skill1 starsChanged 38 days agoMITView on GitHub
Comprehensive PowerPoint (.pptx/.potx) presentation engine. Covers: (1) On-brand corporate deck generation & template extraction via the Brand Engine (extract, comprehend, verify, generate from .pptx/.potx templates and IntermediateDocuments), (2) Creating bespoke decks from scratch via pptxgenjs, (3) Editing, duplicating, and cleaning existing slides via OpenXML surgery (add_slide.py, clean.py), (4) Slide thumbnail analysis & visual grid (thumbnail.py), (5) Native chart and schema validation (validate.py), and (6) Headless PDF rendering (soffice.py). Trigger on any mention of slide decks, presentations, pitch decks, .pptx, .potx, brand deck templates, or PowerPoint manipulation.
- Installs packages
194 other projects use a version of this, 17 of them edited.
Adopted by
Most recently taken up by
- CloudChef/atlasclaw-providerstheir own version, first seen Nov 8, 2026
- holon-run/holontheir own version, first seen Nov 8, 2026
- rvdbreemen/OTGW-firmwaretheir own version, first seen Nov 8, 2026
- BrightGold70/skillstheir own version, first seen Nov 8, 2026
- Liang-MH/skillstheir own version, first seen Nov 8, 2026
- EvanLee2004/finance-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use file-reading, context7-efficient and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SeifBenayedSkillfile-reading
Use this skill when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploaded_files block. This skill is a router: it tells you which tool to use for each file type (pdf, docx, xlsx, csv, json, images, archives, ebooks) so you read the right amount the right way instead of blindly running cat on a binary. Triggers: any mention of /mnt/user-data/uploads/, an uploaded_files section, a file_path tag, or a user asking about an uploaded file you have not yet read. Do NOT use this skill if the file content is already visible in your context inside a documents block — you already have it.
Also in 5 projects that use this
hfzarslanSkillcontext7-efficient
Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.
Also in 5 projects that use this
SeifBenayedSkillpdf-reading
Use this skill when you need to read, inspect, or extract content from PDF files — especially when file content is NOT in your context and you need to read it from disk. Covers content inventory, text extraction, page rasterization for visual inspection, embedded image/attachment/table/form-field extraction, and choosing the right reading strategy for different document types (text-heavy, scanned, slide-decks, forms, data-heavy). Do NOT use this skill for PDF creation, form filling, merging, splitting, watermarking, or encryption — use the pdf skill instead.
Also in 6 projects that use this
amirbironSkillimport-memory
Import a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data.
Also in 5 projects that use this
unicorn-pluginsSkillproduct-self-knowledge
Anthropic 제품 지식 — Claude Code, Claude API, Claude.ai 관련 정확한 정보 제공
Also in 8 projects that use this
AbdullahMalik17Skillconfiguring-dapr-pubsub
Configures Dapr pub/sub components for event-driven microservices with Kafka or Redis. Use when wiring agent-to-agent communication, setting up event subscriptions, or integrating Dapr sidecars. Covers component configuration, subscription patterns, publishing events, and Kubernetes deployment. NOT when using direct Kafka clients or non-Dapr messaging patterns.
Also in 3 projects that use this
Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 17
- anthropics/skills★ 189k11% same
- K-Dense-AI/claude-scientific-writer★ 2.6k11% same
- antgroup/llm-oss-landscape★ 55311% same
- MarcelLeon/skills-zh★ 4212% same
- LiChangZheng10086/doyin_ai_video★ 3011% same
- skateddu/claude-code-python-setup★ 2811% same
- jaskirat1616/grok-skills★ 2211% same
- PracticalSwan/agent-skills★ 2211% same
- Hassaan146/claude-skills★ 1811% same
- delorenj/skills★ 1710% same
7 more not listed
Wrote their own version · 177
- netease-youdao/LobsterAI★ 6.2ksame name
- OpenBMB/PilotDeck★ 5ksame name
- nextlevelbuilder/goclaw★ 3.7ksame name
- jjyaoao/HelloAgents★ 3.2ksame name
- OpenCoworkAI/open-cowork★ 2.2ksame name
- ChenglinPoly/infiAgent★ 1.2ksame name
- polyuiislab/infiAgent★ 1.2ksame name
- melandlabs/openloomi★ 1ksame name
- freestylefly/wesight★ 969same name
- LeonChaoX/qinyan-academic-skills★ 910same name
167 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- citation-verifierSkill
- docxSkill
- research-reviewerSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 189 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Use this pathway when the user provides or references a company presentation template (.pptx / .potx) or asks to "match our deck template", …
- Very specific: line 40
Run preflight (python scripts/cli.py doctor) before extraction or generation to verify system readiness.
- Very specific: line 43
Author role-first, not layout-first: Do not put style names, colors, fonts, or raw geometry in an IntermediateDocument (idoc.json).
- Very specific: line 77
Keep charts native: Use addChart() with {type, data, options}.
“Common” is measured: kept by at least 6 in 10 of the 189 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Unified PPTX Creation, Editing, Brand & Analysis Suite
A .pptx is a ZIP archive of OpenXML files. Choose your approach based on task requirements:
| Task / Domain | Engine / Approach | When to Choose |
| On-Brand Corporate Deck | scripts/brandkit/ (scripts/cli.py) | Extracting reusable Brand Profiles from company .pptx/.potx templates and generating on-brand decks fail-closed from IntermediateDocuments. |
| Create Bespoke Deck | pptxgenjs (Node.js script) | Building brand-new decks from scratch with complete programmatic design, shapes, and custom layouts. |
| Edit Existing Deck / Duplicate | scripts/add_slide.py, clean.py | Duplicating layout slides, removing orphaned media, reordering slides, or surgical OpenXML edits. |
| Slide Thumbnails & Inspection | scripts/thumbnail.py | Generating visual overview grids of template slides to select master layouts. |
| Validate Schema & Charts | scripts/office/validate.py | Validating OpenXML schema compliance, slide relationships, and native chart configurations. |
1. On-Brand Corporate Deck Governance (Brand Engine)
Use this pathway when the user provides or references a company presentation template (.pptx / .potx) or asks to "match our deck template", "use our brand kit", or generate an on-brand presentation from an outline or draft.
The Seven Verbs
The engine implements three deterministic core verbs plus four model-assisted learning verbs:
| Verb | Input | Output | CLI Command |
| extract | A company .pptx or .potx template | A reusable Brand Profile (brand-kit/<name>/) | python scripts/cli.py extract --name <brand> --template <template.pptx> |
| comprehend (optional) | Saved profile + model-authored comprehension.json | Profile with validated, cached comprehension block | python scripts/cli.py comprehend --name <brand> --input comprehension.json |
| verify | Saved Brand Profile | QA findings + deterministic verdict | python scripts/cli.py verify --name <brand> |
| generate | Content (IntermediateDocument) + profile | New on-brand .pptx | python scripts/cli.py generate --name <brand> --input idoc.json -o out.pptx |
| learn | Profile's cross-run history | Recurring findings distilled to shell-frozen overrides | python scripts/cli.py learn --name <brand> --accept |
| propose-overrides | Residual issues + proposal | Shell-backed corrections fail-closed | python scripts/cli.py propose-overrides --name <brand> --input overrides.json --accept |
| refine | User feedback delta | Comprehension overlaid for future generations | python scripts/cli.py refine --name <brand> --input refinement.json --accept |
Hard Rules for Brand Decks
scripts/cli.py(orscripts/brand_cli.py) is the launcher. It automatically resolves the engine root.- Run preflight (
python scripts/cli.py doctor) before extraction or generation to verify system readiness. - Extract opens the template read-only and saves
brand-kit/<name>/template/shell.pptxbyte-for-byte. - Generate opens the saved shell and resolves every semantic block through
profile.json. - Author role-first, not layout-first: Do not put style names, colors, fonts, or raw geometry in an
IntermediateDocument(idoc.json). Consultbrand-kit/<name>/PROFILE.mdfor role vocabulary. - See
references/comprehension.mdandreferences/visual-audit.mdfor full details.
2. Scripts Reference
Paths are relative to this skill's directory. Everything else is plain Python, node, or shell.
| Script | What it does |
scripts/cli.py | Brand engine launcher for doctor, extract, comprehend, verify, generate, learn, refine. |
scripts/thumbnail.py deck.pptx [prefix] | Labeled grid of every slide, for picking template layouts. .pptx only. Pass prefix — it defaults to thumbnails. |
scripts/add_slide.py unpacked/ slide2.xml [--after slideN.xml] | Duplicate a slide (or a slideLayoutN.xml) with package bookkeeping. Also takes a .pptx directly with -o out.pptx. |
scripts/clean.py unpacked/ | Delete slides, media, and rels no longer referenced. Run after <p:sldIdLst> is final. |
scripts/office/validate.py deck.pptx [--original src.pptx] | Schema, relationship, content-type, chart, and slide checks. Pass --original for template-derived decks to baseline. |
scripts/office/soffice.py --headless --convert-to pdf deck.pptx | Headless LibreOffice wrapper for PDF generation and visual QA. |
3. Creating with pptxgenjs — Gotchas & Rules
pptxgenjs is preinstalled — write the script and require('pptxgenjs') directly. Only if that require fails: npm install pptxgenjs.
- Set
pres.layoutbefore adding slides. The default canvas isLAYOUT_16x9= 10" × 5.625", not 13.3" wide. (LAYOUT_WIDEis 13.3" × 7.5".) - Hex colors: never
#, never 8 digits.color: "FF0000". Both"#FF0000"and alpha baked into hex ("00000020") corrupt the file. For translucency:transparency: 0-100on fills and images,opacity: 0.0-1.0on shadows. - pptxgenjs mutates option objects in place (converts values to EMU on first use). Never share one options object across two calls.
- Shadow
offsetmust be ≥ 0 — negative offset corrupts the file. letterSpacingis silently ignored — usecharSpacing.- Lists:
bullet: trueon each item, never a literal•. Space bulleted paragraphs withparaSpaceAfter, notlineSpacing. - One
new pptxgen()per output file — never reuse an instance. rectRadiusonly works onROUNDED_RECTANGLE, notRECTANGLE.- Text boxes have built-in internal padding — set
margin: 0whenever text must align with a shape or line. - Speaker notes go in
slide.addNotes("...")(plain text, once per slide). - Keep charts native. Use
addChart()with{type, data, options}. On a stacked bar/column chart,dataLabelPositionmust bectr,inEnd, orinBase(outEndcorrupts the file). - A combo series using
secondaryValAxis/secondaryCatAxisneeds bothvalAxesandcatAxeson the chart options, two entries each. - After
writeFile(), runpython scripts/office/validate.py deck.pptx.
4. Editing Existing Decks & Templates
Pick layouts first:
python scripts/thumbnail.py template.pptx template-thumbsPerform slide surgery:
python3 -c "import sys,zipfile; zipfile.ZipFile(sys.argv[1]).extractall('unpacked')" deck.pptx
python scripts/add_slide.py unpacked/ slide2.xml --after slide2.xml # duplicate slide
# edit slide content in ppt/slides/slideN.xml
python scripts/clean.py unpacked/ # clean orphaned media/rels
(cd unpacked && rm -f ../out.pptx && zip -Xr ../out.pptx .)
python scripts/office/validate.py out.pptx --original deck.pptx5. Visual QA & Verification
# 1. Content check
markitdown output.pptx
# 2. Check for leftover placeholder text
markitdown output.pptx | grep -iE "\bx{3,}\b|lorem|ipsum|\bTODO|\[insert|this.*(page|slide).*layout"
# 3. Schema & integrity validation
python scripts/office/validate.py output.pptx
# 4. Render to images for visual review
python scripts/office/soffice.py --headless --convert-to pdf output.pptx
rm -f slide-*.jpg
pdftoppm -jpeg -r 150 output.pdf slide
ls -1 "$PWD"/slide-*.jpgDependencies
pptxgenjs (npm) · python-pptx · openpyxl · markitdown[pptx] · Pillow · defusedxml · lxml · LibreOffice (soffice) · pdftoppm (Poppler)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

